敏感内容处置器

v1.2.0

支持关键词脱敏、文件加密和水印添加,对扫描出的敏感内容进行合规处置并可发送通知,需先使用敏感内容扫描器。

0· 153·0 current·0 all-time
byqing@qinkai25

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for qinkai25/sensitive-content-disposal.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "敏感内容处置器" (qinkai25/sensitive-content-disposal) from ClawHub.
Skill page: https://clawhub.ai/qinkai25/sensitive-content-disposal
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install sensitive-content-disposal

ClawHub CLI

Package manager switcher

npx clawhub@latest install sensitive-content-disposal
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
medium confidence
Purpose & Capability
Name/description (sensitive content disposal: redaction + encryption + notifications) match the shipped files and dependencies (docx/openpyxl/python-pptx/PyMuPDF/requests). There are no unrelated environment variables or surprising binaries required.
Instruction Scope
SKILL.md and README describe only file redaction/encryption and sending notifications to Feishu/WeCom (webhooks). That matches the code. However the instructions explicitly state that the encryption password may be included in notifications and the script's processing results include the password—this means secrets chosen by the user can be transmitted to external webhook endpoints. The README also allows overwrite of original files (dangerous if used unintentionally).
Install Mechanism
No install spec is provided (instruction-only), but the package includes a Python script and requirements.txt. Users must manually install Python dependencies via pip; nothing is downloaded from unknown URLs during install. This is low installation risk but you must run code locally to use it.
!
Credentials
The skill declares no required environment variables or credentials, which is consistent. However the tool accepts webhook URLs or a config file and will (by design) include the encryption password in the output metadata and optionally in webhook notifications. That behavior increases the chance of secret exposure to any configured external endpoint and is disproportionate unless the user intentionally wants the password shared.
Persistence & Privilege
The skill does not request persistent/system-wide privileges and always:false. It does require file write permission for its stated purpose and can overwrite original files if user chooses --overwrite; there is no evidence it alters other skills or system settings.
Assessment
This package appears to do what it says (redact and encrypt files and send notifications), but you should be cautious before running it on sensitive data: - Review the code before use: the encryption implementation uses PBKDF2 to derive a key but then XORs file bytes with that key (weak, nonstandard encryption). Do not rely on it for high-sensitivity data. - The tool records and can send the encryption password in the result metadata and in webhook notifications. Only configure trusted webhook endpoints and avoid sending passwords unless you accept that exposure. - Back up original files before running; the tool can overwrite originals if --overwrite is used. - Install dependencies locally in an isolated environment (virtualenv) using requirements.txt; inspect any network calls the script makes (requests usage) and only point webhooks to trusted URLs. - If you need stronger guarantees, replace the encryption routine with a well-reviewed library (e.g., use standard AES/GCM tooling) and remove sending of passwords in notifications. Confidence is medium because the provided script listing was truncated; review the full scripts/disposal.py before trusting it with sensitive production data.

Like a lobster shell, security has layers — review code before you run it.

latestvk97751fbgeevtatv7v435r98xx858094
153downloads
0stars
3versions
Updated 6d ago
v1.2.0
MIT-0

合规处置工具(免费版)

🎯 功能说明

对扫描发现的敏感内容进行合规处置,支持 两种 处置方式和通知功能。

免费使用 —— 无需订阅

👤 适用人群

  • 🔒 安全合规人员
  • 📋 文档审核人员
  • 🛡️ 数据保护专员
  • 🏢 企业信息安全部门

🚀 两种处置方式

方式一:关键词脱敏

操作

  1. 附件:扫描报告或文档文件
  2. 说:"脱敏处理",告诉处置粒度

三种脱敏粒度

粒度示例说明
部分替换13812345678138****5678保留首尾,中间替换
关键字替换密码:123456密码:[REDACTED]完整替换敏感词
正则替换110101199001011234110101********1234按正则规则替换中间

支持的敏感类型

  • 🔢 身份证号
  • 📱 手机号码
  • 💳 银行卡号
  • ✉️ 邮箱地址
  • 🔑 密码/密钥

方式二:文件加密

操作

  1. 附件:要加密的文件
  2. 说:"加密文件"
  3. 输入密码(系统会提示您输入)

加密选项

  • 🔐 设置加密密码
  • 📧 发送到邮箱
  • 💬 发送到飞书/微信

📋 保存方式

处置完成后,系统会提示您选择保存方式:

方式说明
覆盖原文件直接替换原文件(谨慎操作)
保存为新文件生成如 原文件_脱敏版.docx(推荐)

📢 通知功能

处置完成后,可发送通知到:

渠道设置
📧 邮箱关联邮箱地址
💬 飞书配置飞书 Webhook
💬 微信配置企业微信 Webhook

通知内容

  • 处置类型(脱敏/加密)
  • 处置文件数量
  • 处置时间
  • 密码(如加密)

📁 支持的文件格式

类型格式脱敏加密
文本txt, md, json, xml, csv
Worddocx
Excelxlsx
PowerPointpptx
PDFpdf

💡 使用流程

1️⃣ 扫描文档
   └─ 使用"敏感内容扫描器"扫描文档

2️⃣ 查看报告
   └─ 查看扫描报告,了解敏感内容位置

3️⃣ 选择处置
   └─ 附件 + "脱敏处理" 或 "加密文件"

4️⃣ 设置参数
   └─ 选择脱敏粒度、输入密码等

5️⃣ 选择保存
   └─ 覆盖原文件 或 保存为新文件

6️⃣ 发送通知(可选)
   └─ 发送到邮箱/飞书/微信

⚠️ 注意事项

  1. 备份原文件:建议先备份重要文件
  2. 密码安全:加密密码请妥善保管
  3. 不可逆操作:脱敏操作不可逆,请确认后再执行
  4. 权限要求:需要文件写入权限

🔧 技术信息(可选了解)

处置脚本scripts/disposal.py

依赖库

  • python-docx - Word文档处理
  • openpyxl - Excel处理
  • python-pptx - PPT处理
  • PyMuPDF - PDF处理

版本:1.2.0 更新日期:2026-04-21 定价:免费版

Comments

Loading comments...